Some more info on what we are doing:
All is reverse proxy.
We have a fairly small object set (10k) the most active can fit into
512MB of memory. We have tested squid on a dual 2.4Ghz P4 with 2 GB ram
and dual 18GB 15k drives. We are running two squid instances per box.
I know this isn't optimal, but it's what we have.
What we are seeing is that as we approach 175k requests/min/instance,
response time begins to climb and then the server becomes unresponsive.
I grabbed the latest 3 snapshot and it seems faster, but I couldn't get
the CPU profiling to compile, so I'm not sure were I should begin :(
On Wed, 20 Nov 2002 14:12:49 -0600
Joe Cooper <joe@swelltech.com> wrote:
> On that note, I'll finally be posting some benchmarks of 2.5
Received on Thu Nov 21 2002 - 09:59:07 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:18:45 MST